Research Article
Machine Learning-Based Facial Beauty Prediction and Analysis of Frontal Facial Images Using Facial Landmarks and Traditional Image Descriptors
Table 11
Performance of each model according to MSE for 11–25 features.
| S. No. | Number of features | LR | KNN | RF | ANN |
| 1. | 11 | 0.2246 | 0.2119 | 0.2019 | 0.2159 | 2. | 12 | 0.2458 | 0.2274 | 0.2307 | 0.242 | 3. | 13 | 0.2329 | 0.1839 | 0.2853 | 0.2295 | 4. | 14 | 0.2462 | 0.1773 | 0.2724 | 0.239 | 5. | 15 | 0.2404 | 0.1897 | 0.2224 | 0.3072 | 6. | 16 | 0.2033 | 0.1886 | 0.3046 | 0.2963 | 7. | 17 | 0.1986 | 0.1985 | 0.2379 | 0.2038 | 8. | 18 | 0.1987 | 0.2098 | 0.2339 | 0.2983 | 9. | 19 | 0.2031 | 0.2171 | 0.2639 | 0.2096 | 10. | 20 | 0.2056 | 0.2069 | 0.2658 | 0.2165 | 11. | 21 | 0.2098 | 0.2154 | 0.2645 | 0.2148 | 12. | 22 | 0.2154 | 0.2167 | 0.2594 | 0.2259 | 13. | 23 | 0.2106 | 0.2098 | 0.2561 | 0.226 | 14. | 24 | 0.2198 | 0.2192 | 0.2632 | 0.2197 | 15. | 25 | 0.2046 | 0.2367 | 0.2674 | 0.213 |
|
|